Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2334
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "where."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "where" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    clauses beginning with where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.69
     Majefty
    -0.64
     Shakspeare
    -0.64
     letto
    -0.64
     urbanas
    -0.63
     himſelf
    -0.61
     Efq
    -0.60
     barbati
    -0.58
     sobą
    -0.57
     crdi
    -0.57
    POSITIVE LOGITS
     they
    1.09
     we
    1.05
     there
    1.02
     it
    1.01
     the
    0.99
     you
    0.93
     he
    0.78
     both
    0.72
    帖最后由
    0.72
    SuppressMessage
    0.68
    Activations Density 0.166%

    No Known Activations